Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4011 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.5129. Min Act: -0.0000

Data Index: 491762 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4365. Min Act: -0.0000

Data Index: 233593 (The Pile)

Max Activating Token Index: 893

Text #2

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1676945 (The Pile)

Max Activating Token Index: 930

Text #3

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4535. Min Act: -0.0000

Data Index: 540607 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1819850 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1310344 (The Pile)

Max Activating Token Index: 589

Text #6

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1734094 (The Pile)

Max Activating Token Index: 505

Text #7

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1714107 (The Pile)

Max Activating Token Index: 208

Text #8

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1073890 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3694. Min Act: -0.0000

Data Index: 507603 (The Pile)

Max Activating Token Index: 362

Text #10

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1066177 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3878. Min Act: -0.0000

Data Index: 131637 (The Pile)

Max Activating Token Index: 924

Text #12

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1257043 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3692. Min Act: 0.0000

Data Index: 1067288 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1363500 (The Pile)

Max Activating Token Index: 594

Text #15

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3479. Min Act: 0.0000

Data Index: 273213 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3716. Min Act: -0.0000

Data Index: 488839 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3335. Min Act: -0.0000

Data Index: 38052 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3387. Min Act: -0.0000

Data Index: 536634 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 0.5129. Min Range: -0.5129

Max Act: 0.3624. Min Act: 0.0000

Data Index: 1599127 (The Pile)

Max Activating Token Index: 588